import pandas as pd
import numpy as np
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import confusion_matrix,accuracy_score

from keras.models import Sequential
from keras.layers import Dense, Dropout, LSTM, Activation
from keras.callbacks import EarlyStopping

import matplotlib.pyplot as plt
plt.style.use('ggplot')
%matplotlib inline

Using TensorFlow backend.

dataset_train=pd.read_csv('PM_train.txt',sep=' ',header=None).drop([26,27],axis=1)
col_names = ['id','cycle','setting1','setting2','setting3','s1','s2','s3','s4','s5','s6','s7','s8','s9','s10','s11','s12','s13','s14','s15','s16','s17','s18','s19','s20','s21']
dataset_train.columns=col_names
print('Shape of Train dataset: ',dataset_train.shape)
dataset_train.head()

Shape of Train dataset:  (20631, 26)

	id	cycle	setting1	setting2	setting3	s1	s2	s3	s4	s5	...	s12	s13	s14	s15	s16	s17	s18	s19	s20	s21
0	1	1	-0.0007	-0.0004	100.0	518.67	641.82	1589.70	1400.60	14.62	...	521.66	2388.02	8138.62	8.4195	0.03	392	2388	100.0	39.06	23.4190
1	1	2	0.0019	-0.0003	100.0	518.67	642.15	1591.82	1403.14	14.62	...	522.28	2388.07	8131.49	8.4318	0.03	392	2388	100.0	39.00	23.4236
2	1	3	-0.0043	0.0003	100.0	518.67	642.35	1587.99	1404.20	14.62	...	522.42	2388.03	8133.23	8.4178	0.03	390	2388	100.0	38.95	23.3442
3	1	4	0.0007	0.0000	100.0	518.67	642.35	1582.79	1401.87	14.62	...	522.86	2388.08	8133.83	8.3682	0.03	392	2388	100.0	38.88	23.3739
4	1	5	-0.0019	-0.0002	100.0	518.67	642.37	1582.85	1406.22	14.62	...	522.19	2388.04	8133.80	8.4294	0.03	393	2388	100.0	38.90	23.4044

5 rows × 26 columns

dataset_train['id'].value_counts()

69    362
92    341
96    336
67    313
83    293
     ... 
24    147
57    137
70    137
91    135
39    128
Name: id, Length: 100, dtype: int64

dataset_test=pd.read_csv('PM_test.txt',sep=' ',header=None).drop([26,27],axis=1)
dataset_test.columns=col_names
#dataset_test.head()
print('Shape of Test dataset: ',dataset_train.shape)
dataset_train.head()

Shape of Test dataset:  (20631, 26)

	id	cycle	setting1	setting2	setting3	s1	s2	s3	s4	s5	...	s12	s13	s14	s15	s16	s17	s18	s19	s20	s21
0	1	1	-0.0007	-0.0004	100.0	518.67	641.82	1589.70	1400.60	14.62	...	521.66	2388.02	8138.62	8.4195	0.03	392	2388	100.0	39.06	23.4190
1	1	2	0.0019	-0.0003	100.0	518.67	642.15	1591.82	1403.14	14.62	...	522.28	2388.07	8131.49	8.4318	0.03	392	2388	100.0	39.00	23.4236
2	1	3	-0.0043	0.0003	100.0	518.67	642.35	1587.99	1404.20	14.62	...	522.42	2388.03	8133.23	8.4178	0.03	390	2388	100.0	38.95	23.3442
3	1	4	0.0007	0.0000	100.0	518.67	642.35	1582.79	1401.87	14.62	...	522.86	2388.08	8133.83	8.3682	0.03	392	2388	100.0	38.88	23.3739
4	1	5	-0.0019	-0.0002	100.0	518.67	642.37	1582.85	1406.22	14.62	...	522.19	2388.04	8133.80	8.4294	0.03	393	2388	100.0	38.90	23.4044

5 rows × 26 columns

pm_truth=pd.read_csv('PM_truth.txt',sep=' ',header=None).drop([1],axis=1)
pm_truth.columns=['more']
pm_truth['id']=pm_truth.index+1
pm_truth.head()

	more	id
0	112	1
1	98	2
2	69	3
3	82	4
4	91	5

pm_truth.shape

(100, 2)

rul = pd.DataFrame(dataset_test.groupby('id')['cycle'].max()).reset_index()
rul.columns = ['id', 'max']
rul.head()

	id	max
0	1	31
1	2	49
2	3	126
3	4	106
4	5	98

rul.shape

(100, 2)

pm_truth['rtf']=pm_truth['more']+rul['max']
pm_truth.head()

	more	id	rtf
0	112	1	143
1	98	2	147
2	69	3	195
3	82	4	188
4	91	5	189

pm_truth.shape

(100, 3)

pm_truth.drop('more', axis=1, inplace=True)
dataset_test=dataset_test.merge(pm_truth,on=['id'],how='left')
dataset_test['ttf']=dataset_test['rtf'] - dataset_test['cycle']
dataset_test.drop('rtf', axis=1, inplace=True)
dataset_test.head()

	id	cycle	setting1	setting2	setting3	s1	s2	s3	s4	s5	...	s13	s14	s15	s16	s17	s18	s19	s20	s21	ttf
0	1	1	0.0023	0.0003	100.0	518.67	643.02	1585.29	1398.21	14.62	...	2388.03	8125.55	8.4052	0.03	392	2388	100.0	38.86	23.3735	142
1	1	2	-0.0027	-0.0003	100.0	518.67	641.71	1588.45	1395.42	14.62	...	2388.06	8139.62	8.3803	0.03	393	2388	100.0	39.02	23.3916	141
2	1	3	0.0003	0.0001	100.0	518.67	642.46	1586.94	1401.34	14.62	...	2388.03	8130.10	8.4441	0.03	393	2388	100.0	39.08	23.4166	140
3	1	4	0.0042	0.0000	100.0	518.67	642.44	1584.12	1406.42	14.62	...	2388.05	8132.90	8.3917	0.03	391	2388	100.0	39.00	23.3737	139
4	1	5	0.0014	0.0000	100.0	518.67	642.51	1587.19	1401.92	14.62	...	2388.03	8129.54	8.4031	0.03	390	2388	100.0	38.99	23.4130	138

5 rows × 27 columns

dataset_test.shape

(13096, 27)

dataset_train['ttf'] = dataset_train.groupby(['id'])['cycle'].transform(max)-dataset_train['cycle']
dataset_train.head()

	id	cycle	setting1	setting2	setting3	s1	s2	s3	s4	s5	...	s13	s14	s15	s16	s17	s18	s19	s20	s21	ttf
0	1	1	-0.0007	-0.0004	100.0	518.67	641.82	1589.70	1400.60	14.62	...	2388.02	8138.62	8.4195	0.03	392	2388	100.0	39.06	23.4190	191
1	1	2	0.0019	-0.0003	100.0	518.67	642.15	1591.82	1403.14	14.62	...	2388.07	8131.49	8.4318	0.03	392	2388	100.0	39.00	23.4236	190
2	1	3	-0.0043	0.0003	100.0	518.67	642.35	1587.99	1404.20	14.62	...	2388.03	8133.23	8.4178	0.03	390	2388	100.0	38.95	23.3442	189
3	1	4	0.0007	0.0000	100.0	518.67	642.35	1582.79	1401.87	14.62	...	2388.08	8133.83	8.3682	0.03	392	2388	100.0	38.88	23.3739	188
4	1	5	-0.0019	-0.0002	100.0	518.67	642.37	1582.85	1406.22	14.62	...	2388.04	8133.80	8.4294	0.03	393	2388	100.0	38.90	23.4044	187

5 rows × 27 columns

dataset_train.shape

(20631, 27)

dataset_train['ttf'].value_counts()

0      100
123    100
121    100
89     100
73     100
      ... 
341      1
356      1
355      1
354      1
351      1
Name: ttf, Length: 362, dtype: int64

df_train=dataset_train.copy()
df_test=dataset_test.copy()
period=30
df_train['label_bc'] = df_train['ttf'].apply(lambda x: 1 if x <= period else 0)
df_test['label_bc'] = df_test['ttf'].apply(lambda x: 1 if x <= period else 0)
df_train.head()

	id	cycle	setting1	setting2	setting3	s1	s2	s3	s4	s5	...	s14	s15	s16	s17	s18	s19	s20	s21	ttf	label_bc
0	1	1	-0.0007	-0.0004	100.0	518.67	641.82	1589.70	1400.60	14.62	...	8138.62	8.4195	0.03	392	2388	100.0	39.06	23.4190	191	0
1	1	2	0.0019	-0.0003	100.0	518.67	642.15	1591.82	1403.14	14.62	...	8131.49	8.4318	0.03	392	2388	100.0	39.00	23.4236	190	0
2	1	3	-0.0043	0.0003	100.0	518.67	642.35	1587.99	1404.20	14.62	...	8133.23	8.4178	0.03	390	2388	100.0	38.95	23.3442	189	0
3	1	4	0.0007	0.0000	100.0	518.67	642.35	1582.79	1401.87	14.62	...	8133.83	8.3682	0.03	392	2388	100.0	38.88	23.3739	188	0
4	1	5	-0.0019	-0.0002	100.0	518.67	642.37	1582.85	1406.22	14.62	...	8133.80	8.4294	0.03	393	2388	100.0	38.90	23.4044	187	0

5 rows × 28 columns

df_train['label_bc'].value_counts()

0    17531
1     3100
Name: label_bc, dtype: int64

features_col_name=['setting1', 'setting2', 'setting3', 's1', 's2', 's3', 's4', 's5', 's6', 's7', 's8', 's9', 's10', 's11',
                   's12', 's13', 's14', 's15', 's16', 's17', 's18', 's19', 's20', 's21']
target_col_name='label_bc'

sc=MinMaxScaler()
df_train[features_col_name]=sc.fit_transform(df_train[features_col_name])
df_test[features_col_name]=sc.transform(df_test[features_col_name])

df_train.head()

	id	cycle	setting1	setting2	setting3	s1	s2	s3	s4	s5	...	s14	s15	s16	s17	s18	s19	s20	s21	ttf	label_bc
0	1	1	0.459770	0.166667	0.0	0.0	0.183735	0.406802	0.309757	0.0	...	0.199608	0.363986	0.0	0.333333	0.0	0.0	0.713178	0.724662	191	0
1	1	2	0.609195	0.250000	0.0	0.0	0.283133	0.453019	0.352633	0.0	...	0.162813	0.411312	0.0	0.333333	0.0	0.0	0.666667	0.731014	190	0
2	1	3	0.252874	0.750000	0.0	0.0	0.343373	0.369523	0.370527	0.0	...	0.171793	0.357445	0.0	0.166667	0.0	0.0	0.627907	0.621375	189	0
3	1	4	0.540230	0.500000	0.0	0.0	0.343373	0.256159	0.331195	0.0	...	0.174889	0.166603	0.0	0.333333	0.0	0.0	0.573643	0.662386	188	0
4	1	5	0.390805	0.333333	0.0	0.0	0.349398	0.257467	0.404625	0.0	...	0.174734	0.402078	0.0	0.416667	0.0	0.0	0.589147	0.704502	187	0

5 rows × 28 columns

df_train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 20631 entries, 0 to 20630
Data columns (total 28 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   id        20631 non-null  int64  
 1   cycle     20631 non-null  int64  
 2   setting1  20631 non-null  float64
 3   setting2  20631 non-null  float64
 4   setting3  20631 non-null  float64
 5   s1        20631 non-null  float64
 6   s2        20631 non-null  float64
 7   s3        20631 non-null  float64
 8   s4        20631 non-null  float64
 9   s5        20631 non-null  float64
 10  s6        20631 non-null  float64
 11  s7        20631 non-null  float64
 12  s8        20631 non-null  float64
 13  s9        20631 non-null  float64
 14  s10       20631 non-null  float64
 15  s11       20631 non-null  float64
 16  s12       20631 non-null  float64
 17  s13       20631 non-null  float64
 18  s14       20631 non-null  float64
 19  s15       20631 non-null  float64
 20  s16       20631 non-null  float64
 21  s17       20631 non-null  float64
 22  s18       20631 non-null  float64
 23  s19       20631 non-null  float64
 24  s20       20631 non-null  float64
 25  s21       20631 non-null  float64
 26  ttf       20631 non-null  int64  
 27  label_bc  20631 non-null  int64  
dtypes: float64(24), int64(4)
memory usage: 4.4 MB

df_train['ttf'].min()

0

df_train['ttf'].max()

361

df_train.iloc[0,:]

id            1.000000
cycle         1.000000
setting1      0.459770
setting2      0.166667
setting3      0.000000
s1            0.000000
s2            0.183735
s3            0.406802
s4            0.309757
s5            0.000000
s6            1.000000
s7            0.726248
s8            0.242424
s9            0.109755
s10           0.000000
s11           0.369048
s12           0.633262
s13           0.205882
s14           0.199608
s15           0.363986
s16           0.000000
s17           0.333333
s18           0.000000
s19           0.000000
s20           0.713178
s21           0.724662
ttf         191.000000
label_bc      0.000000
Name: 0, dtype: float64

import seaborn as sns
sns.pairplot(df_train)

<seaborn.axisgrid.PairGrid at 0x1e9af779978>

x_train = df_train.iloc[:,:-1].values
y_train = df_train.iloc[:,-1:].values

from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
model.fit(x_train,y_train)

c:\users\naren\appdata\local\programs\python\python37\lib\site-packages\sklearn\utils\validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  return f(**kwargs)
c:\users\naren\appdata\local\programs\python\python37\lib\site-packages\sklearn\linear_model\_logistic.py:764: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG)

LogisticRegression()

import joblib

joblib.dump(model, "engine_model.sav")

['engine_model.sav']

x_test = df_test.iloc[:,:-1].values
y_test = df_test.iloc[:,-1:].values

y_predlog = model.predict(x_test)

from sklearn.metrics import accuracy_score
accuracy_score(y_predlog,y_test)

0.9993127672571778

from sklearn.metrics import confusion_matrix
cm1 = confusion_matrix(y_test,y_predlog)
cm1

array([[12763,     1],
       [    8,   324]], dtype=int64)

import numpy as np
from sklearn.linear_model import LogisticRegression
import joblib

id -> 1-100 (int) cycle -> 1-400 (int) settings, sensors -> 0-1 (float) ttf -> 0-361 (int)

inp =[1,1,0.45977,0.166667,0,0,0.183735,0.406802,0.309757,0,1,0.726248,0.242424,0.109755,0,0.369048,0.633262,0.205882,0.199608,0.363986,0,0.333333,0,0,0.713178,0.724662,191]

out=0

model = joblib.load("engine_model.sav")

model.predict([inp])

array([0], dtype=int64)

import random

inp1=[]
inp1.append(random.randint(0,100)) #id
inp1.append(random.randint(0,365)) #cycle
for i in range(0,24):
    inp1.append(random.uniform(0,1))
inp1.append(random.randint(0,365)) #ttf

len(inp1)

27

model.predict([inp1])

array([0], dtype=int64)

import numpy as np
from flask import Flask, request, jsonify, render_template
import joblib
import random

app = Flask(__name__)
model = joblib.load("engine_model.sav")


app = Flask(__name__)

@app.route('/m_predict')
def predict():
    return render_template('Manual_predict.html')

@app.route('/s_predict')
def spredict():
    return render_template('Sensor_predict.html')

@app.route('/y_predict',methods=['POST'])
def y_predict():
    x_test = [[int(x) for x in request.form.values()]]
   
    
    print(x_test)
    a = model.predict(x_test)
    pred = a[0]
    if(pred == 0):
        pred = "No failure expected within 30 days."
    else:
        pred = "Maintenance Required!! Expected a failure within 30 days."
    
    return render_template('Manual_predict.html', prediction_text=pred)

@app.route('/sy_predict',methods=['POST'])
def sy_predict():
    inp1=[]
    inp1.append(random.randint(0,100)) #id
    inp1.append(random.randint(0,365)) #cycle
    for i in range(0,24):
        inp1.append(random.uniform(0,1))
    inp1.append(random.randint(0,365)) #ttf
    pred=model.predict([inp1])
    if(pred == 0):
        pred = "No failure expected within 30 days."
    else:
        pred = "Maintenance Required!! Expected a failure within 30 days."
    return render_template('Sensor_predict.html', prediction_text=pred,data=inp1)

if __name__ == '__main__':
    app.run(host='0.0.0.0', debug=True)

 * Serving Flask app "__main__" (lazy loading)
 * Environment: production
   WARNING: This is a development server. Do not use it in a production deployment.
   Use a production WSGI server instead.
 * Debug mode: on

 * Restarting with stat

An exception has occurred, use %tb to see the full traceback.

SystemExit: 1

c:\users\naren\appdata\local\programs\python\python37\lib\site-packages\IPython\core\interactiveshell.py:3426: UserWarning: To exit: use 'exit', 'quit', or Ctrl-D.
  warn("To exit: use 'exit', 'quit', or Ctrl-D.", stacklevel=1)